search

zju3dv / manhattan_sdf

Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral
https://zju3dv.github.io/manhattan_sdf/
Other
491 stars 35 forks source link

Run on my own data #34

Closed DanielLiking closed 1 year ago

DanielLiking commented 1 year ago

Could you please tell me the detail steps of running the code on our own data? I am confused with how to prepare the data, like the intrinsic.txt. And I don't know why would this happen image My pics are all 756*504 but I met this mistake. I don't know how to fix it. I hope to receive your reply,THX!

DanielLiking commented 1 year ago

@zju3dv

ghy0324 commented 1 year ago

Hi! Where do you get the generate_poses.py file?

DanielLiking commented 1 year ago

I wrote a .py file based on the author work

ghy0324 commented 1 year ago

You may debug and check the shape of masks.

DanielLiking commented 1 year ago

I fixed it. And I wanna know how to get the pose/*.txt, can you help me out?

ghy0324 commented 1 year ago

Solve the camera poses and save the 4x4 matrices using numpy.savetxt